Read or answer the console's open dialog

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations supplied, the description carries the full burden and delivers: read is read-only, press requires exclusive: true, the guard fields must match what read returned ("" when untitled), and the dialog is re-read afterwards returning closed, replaced, or still open. It goes further than most by warning that what a button does has NO UNDO and that the console's last command does not name the button, so the effect must be checked on the object.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Nearly every clause carries distinct operational information, and the when-to-use condition is front-loaded. It is a dense block of semicolon-joined fragments rather than a structured list, which costs some scannability for a tool with two modes and four optional guard parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by enumerating what read returns (class, title, message, buttons with text and enabled, or open: false) and the three post-press states. For a five-parameter, annotation-free tool with irreversible button presses, that covers everything an agent needs to call it safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 80%, so most parameters are already documented; the description still adds the purpose behind them — expect_title/expect_text exist as a safety comparison against the live dialog, and button must match the exact text read listed and be enabled. It adds a little more with the collapsed-whitespace comparison rule, though it does not restate the action enum values beyond the read/press behaviour split.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource — read the top modal or press one of its buttons — and scopes it precisely as the fallback 'for a dialog no structured tool answers, e.g. a macro's Lua Confirm()'. It also names the sibling that reports the trigger condition (gma3_run_macro) and the siblings that handle their own dialogs, so an agent can separate it from every other tool in the list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives both directions: use it only for dialogs nothing structured covers, and skip it for gma3_save_show and gma3_patch_move which answer their own dialogs. It also prescribes the operating order — read the message first, then press — and states that a mismatched dialog is never answered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.